This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Recognizing Mathematical Expressions Using Tree Transformation
November 2002 (vol. 24 no. 11)
pp. 1455-1467

Abstract—We describe a robust and efficient system for recognizing typeset and handwritten mathematical notation. From a list of symbols with bounding boxes the system analyzes an expression in three successive passes. The Layout Pass constructs a Baseline Structure Tree (BST) describing the two-dimensional arrangement of input symbols. Reading order and operator dominance are used to allow efficient recognition of symbol layout even when symbols deviate greatly from their ideal positions. Next, the Lexical Pass produces a Lexed BST from the initial BST by grouping tokens comprised of multiple input symbols; these include decimal numbers, function names, and symbols comprised of nonoverlapping primitives such as “=”. The Lexical Pass also labels vertical structures such as fractions and accents. The Lexed BST is translated into $\LaTeX$. Additional processing, necessary for producing output for symbolic algebra systems, is carried out in the Expression Analysis Pass. The Lexed BST is translated into an Operator Tree, which describes the order and scope of operations in the input expression. The tree manipulations used in each pass are represented compactly using tree transformations. The compiler-like architecture of the system allows robust handling of unexpected input, increases the scalability of the system, and provides the groundwork for handling dialects of mathematical notation.

[1] D. Blostein and A. Grbavec, “Recognition of Mathematical Notation,” Handbook of Character Recognition and Document Image Analysis, pp. 557-582, World Scientific, 1997.
[2] K. Chan and D. Yeung, “Mathematical Expression Recognition: A Survey,” Int'l J. Document Analysis and Recognition, vol. 3, no. 1, pp. 3-15, Aug. 2000.
[3] A. Kacem, A. Belaïd, and M.B. Ahmed, “Automatic Extraction of Printed Mathematical Formulas Using Fuzzy Logic and Propogation of Context,” Int'l. J. Document Analysis and Recognition, vol. 4, no. 2, pp. 97-108, Dec. 2001.
[4] R.J. Fateman, “How to Find Mathematics on a Scanned Page,” Proc. SPIE, vol. 3967, pp. 98-109, 1999.
[5] B.P. Berman and R.J. Fateman, “Optical Character Recognition for Typeset Mathematics,” Proc. Int'l Symp. Symbolic and Algebraic Computation, pp. 348-353, 1994.
[6] Z.X. Wang and C. Faure, “Structural Analysis of Handwritten Mathematical Expressions,” Proc. Ninth Int'l Conf. Pattern Recognition, pp. 32-34, 1988.
[7] E.G. Miller and P.A. Viola, “Ambiguity and Constraint in Mathematical Expression Recognition,” Proc. 15th Nat'l Conf. Artificial Intelligence, pp. 784-791, 1998.
[8] R. Zanibbi, “Recognition of Mathematics Notation via Computer Using Baseline Structure,” Technical Report, ISBN-0836-0227-2000-439, School of Computing, Queen's Univ., Aug. 2000.
[9] S. Srihari, “From Pixels to Paragraphs: The Use of Contextual Models in Text Recognition,” Proc. Second Int'l. Conf. Document Analysis and Recognition, pp. 416-423, 1993.
[10] T.W. Chaundy, P.R. Barrett, and C. Batey, The Printing of Mathematics. London: Oxford Univ. Press, 1957.
[11] N.J. Higham, Handbook of Writing for the Mathematical Sciences. Philadelphia: SIAM, 1993.
[12] D.E. Knuth, $\big. \TeX\bigr.$and METAFONT—New Directions in Typesetting. Digital Press, 1979.
[13] G. Costagliola, A. De Lucia, and S. Orefice, “A Parsing Methodology for the Implementation of Visual Systems,” IEEE Trans. Software Eng., vol. 23, no. 12, pp. 777-799, Dec. 1997.
[14] H. Lee and M. Lee, “Understanding Mathematical Expressions Using Procedure-Oriented Transformation,” Pattern Recognition, vol. 27, no. 3, pp. 447-457, 1994.
[15] K. Inoue, R. Miyazaki, and M. Suzuki, “Optical Recognition of Printed Mathematical Documents,” Proc. Third Asian Technology Conf. Math., pp. 280-289, 1998.
[16] A. Aho, V. Jeffrey, and D. Ullman, Principles of Compiler Design. Addison-Wesley, 1977.
[17] R. Zanibbi, D. Blostein, and J.R. Cordy, “Baseline Structure Analysis of Handwritten Mathematics Notation,” Proc. Sixth Int'l Conf. Document Analysis and Recognition, pp. 768-773, 2001.
[18] S. Smithies, K. Novins, and J. Arvo, “Equation Entry and Editing via Handwriting and Gesture Recognition,” Behaviour and Information Technology, vol. 20, no. 1, pp. 53-67, 2001.
[19] R. Zanibbi, K. Novins, J. Arvo, and K. Zanibbi, “Aiding Manipulation of Handwritten Mathematical Expressions through Style-Preserving Morphs,” Proc. Graphics Interface, pp. 127-134, 2001.
[20] P.A. Chou, “Recognition of Equations Using a Two-Dimensional Stochastic Context-Free Grammar,” Visual Comm. and Image Processing IV, pp. 852-863, 1989.
[21] A. Grbavec and D. Blostein, “Mathematics Recognition Using Graph Rewriting,” Proc. Third Int'l Conf. Document Analysis and Recognition, pp. 417-421, 1995.
[22] J.R. Cordy, I. Charmichael, and R. Halliday, The TXL Programming Language-Version 10, Jan. 2000.
[23] J.R. Cordy, C.D. Halpern, and E. Promislow, TXL: A Rapid Prototyping System for Programming Language Dialects Computer Languages, vol. 16, no. 1, pp. 97-107, Jan. 1991.
[24] S. Chang, “A Method for the Structural Analysis of Two-Dimensional Mathematical Expressions,” Information Sciences, vol. 2, pp. 253-272, 1970.
[25] R.H. Anderson, “Syntax-Directed Recognition of Hand-Printed Two-Dimensional Equations.” PhD thesis, Harvard Univ., Jan. 1968.
[26] M. Okamoto and B. Miao, “Recognition of Mathematical Expressions by Using the Layout Structures of Symbols,” Proc. First Int'l Conf. Document Analysis and Recognition, vol. 1, pp. 242-250, 1991.
[27] S. Wolfram, The Mathematica Book, version 4. Cambridge Univ. Press, 1999.
[28] F. Garvan, The MAPLE Book. CRC Press, 2001.
[29] I. Phillips, “Methodologies for Using UW Databases for OCR and Image Understanding Systems,” Document Recognition V, SPIE Proc., vol. 3305, pp. 112-127, 1998.
[30] I. Phillips and A. Chhabra, “Empirical Performance Evaluation of Graphics Recognition Systems,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 9, pp. 849-870, Sept. 1999.
[31] E. Brill, “Transformation-Based Error-Driven Parsing,” Recent Advances in Parsing Technology, pp. 1-13, Kluwer Academic, 1996.
[32] E. Charniak, Statistical Language Learning. MIT Press, 1993.
[33] U. Garain and B.B. Chaudhuri, “On Developmentand Statistical Analysis of a Corpus for Printed and Handwritten Expressions,” Proc. Fourth Int'l IAPR Workshop Graphics Recognition, pp. 429-439, Sept. 2001.
[34] A. Belaïd and J. Haton, “A Syntactic Approach for Handwritten Mathematical Formula Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 6, no. 1, pp. 105-111, Jan. 1984.
[35] M. Okamoto, H. Imai, and K. Takagi, “Performance Evaluation of a Robust Method for Mathematical Expression Recognition,” Proc. Sixth Int'l Conf. Document Analysis and Recognition, pp. 121-128, 2001.
[36] K. Chan and D. Yeung, “Error Detection, Error Correction and Performance Evaluation in On-Line Mathematical Expression Recognition,” Pattern Recognition, vol. 34, pp. 1671-1684, 2001.
[37] Y. Eto and M. Suzuki, “Mathematical Formula Recognition Using Virtual Link Network,” Proc. Sixth Int'l Conf. Document Analysis and Recognition, pp. 762-767, 2001.
[38] R. Fukuda, S. I, F. Tamari, X. Ming, and M. Suzuki, “A Technique of Mathematical Expression Structure Analysis for the Handwriting Input System,” Proc. Fifth Int'l Conf. Document Analysis and Recognition, pp. 131-134, 1999.
[39] T. Kanahori and M. Suzuki, “A Recognition Method of Matrices by Using Variable Block Pattern Elements Generating Rectangular Area,” Proc. Fourth Int'l IAPR Workshop Graphics Recognition, pp. 455-469, 2001.
[40] K. Toyozumi, T. Suzuki, K. Mori, and Y. Suenega, “A System for Real-Time Recognition of Handwritten Mathematical Formulas,” Proc. Sixth Int'l Conf. Document Analysis and Recognition, pp. 1059-1063, 2001.
[41] H. Winkler, H. Fahrner, and M. Lang, “A Soft Decision Approach for Structural Analysis of Handwritten Mathematical Expressions,” Proc. Int'l Conf. Acoustics, Speech and Signal Processing, pp. 2459-2462, 1995.
[42] C. Faure and Z.X. Wang, “Automatic Perception of the Structure of Handwritten Mathematical Expressions,” Computer Processing of Handwriting, R. Plamondon and C.G. Leedham, eds., pp. 337-361, World Scientific, 1990.
[43] R. Zanibbi, D. Blostein, and J.R. Cordy, “Directions in Recognizing Tabular Structures of Handwritten Mathematics Notation,” Proc. Fourth Int'l IAPR Workshop Graphics Recognition, pp. 493-499, Sept. 2001.
[44] R.H. Anderson, “Two-Dimensional Mathematical Notation,” Syntactic Pattern Recognition, K.S. Fu, ed., pp. 147-177, New York: Springer Verlag, 1977.

Index Terms:
Document image analysis, recognition of mathematical notation, diagram recognition, tree transformation, graphics recognition.
Citation:
Richard Zanibbi, Dorothea Blostein, James R. Cordy, "Recognizing Mathematical Expressions Using Tree Transformation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 11, pp. 1455-1467, Nov. 2002, doi:10.1109/TPAMI.2002.1046157
Usage of this product signifies your acceptance of the Terms of Use.